“Playwright”

Reference rules for choosing resilient Playwright locators — priority order, scoping, iframes, shadow DOM, dynamic lists, tables and strictness errors.

Diagnose and fix failing or flaky Playwright tests in an existing suite using the executor → healer loop with root-cause classification, without weakening…

Audit an existing Playwright test suite (or specific specs) for coverage, locator quality, assertion strength, isolation, flakiness risk and hard-coded…

Fetch web pages with per-domain method preference: curl (no proxy) → Playwright → Playwright+proxy.

Playrunner

playrunner.dev

Discover Playwright workflows, start runs, and inspect results in Playrunner Cloud.

Browser infrastructure for AI agents: stealth cloud browsers, an open-source Playwright-based framework and deployable functions.

Playwright selector risk checks with healing suggestions and receipts.

Open-source SDK for browser agents that combines natural-language act, extract and observe with Playwright-style control.

Browser DevTools MCP

serkan-ozal

Playwright-powered browser automation and Node.js backend debugging for VS Code and Cursor via MCP.

测试阶段的真实浏览器验证底座。用于页面交互、表单、路由、前端 API、视觉状态和运行时问题验证。优先使用 Playwright MCP 做真实交互验证，使用 Chrome DevTools MCP 做运行时诊断；MCP 不可用时回退到本地 Playwright CLI 脚本。

Discovery-first workflow for writing a new Playwright e2e test from a user story, feature description or bug report.

Toolkit for interacting with and testing local web applications using Playwright.

Explore a live web page or flow with a real browser and produce a verified page map of resilient Playwright locators, without writing tests.

Show the current or a past playwright-autopilot run — phase, heal budget, artifacts and the reasoning trail.

Interactive web application testing with Playwright: UI debugging, screenshots, DOM verification.

Migrate from Cypress or Selenium to Playwright.

Review Playwright tests for quality.

use any website on a user's behalf in a cloud browser: navigate, sign in, fill forms, buy, download.

AGENTS.md from microsoft/playwright: 178 lines covering Build, Lint and type check, Test Commands, DEPS System and more.

Invoke when the agent needs Playwright to drive a web UI behind an interactive authentication flow that a throwaway isolated browser cannot complete, when…

CloakBrowser MCP

swimmwatch

Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium.

5-level verification pyramid: static→unit→Playwright E2E (homepage-first, 6bp)→AI visual→post-deploy.

统一自动化入口。覆盖浏览器自动化（Playwright）和 Windows 桌面应用自动化（OpenReverse）。 浏览器场景：打开网页、点击、填表、爬取、截图、自动化登录、渗透页面交互。 桌面场景：操作 IDA/x64dbg 等 GUI 工具、Windows UI…

Specialist subagent: Playwright, Cypress, and visual regression testing specialist.